Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Risk dispersion type stock selection algorithm based on stock association network clustering

An associative network, decentralized technology, applied in computing, computer components, data processing applications, etc., can solve problems such as insufficient consideration of stock connection relationships, and achieve the effect of high return to risk ratio

Pending Publication Date: 2022-05-31
NORTHWEST UNIV(CN)
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of the defects or deficiencies in the above-mentioned prior art, the purpose of the present invention is to provide a risk-dispersed stock selection algorithm based on stock association network clustering, which solves the problem of concrete representation of association relations among individual stocks in the stock market, and at the same time It also solves the problem of insufficient consideration of the stock connection relationship in the stock classification method, and finally realizes the construction of diversified stock portfolios

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Risk dispersion type stock selection algorithm based on stock association network clustering
  • Risk dispersion type stock selection algorithm based on stock association network clustering
  • Risk dispersion type stock selection algorithm based on stock association network clustering

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0032] see figure 2 , the present embodiment provides a risk-dispersed stock selection algorithm based on stock association network clustering, including the following steps:

[0033] Step 1: Construct a stock association network based on the stock index core principal component features:

[0034] In this embodiment, considering both the technical trend and the fundamental situation of the stock, 21 commonly used stock trading indexes and fundamental indexes are selected as the stock index set, as shown in Table 1 and Table 2 below. Individual stocks are represented by weekly data from the Equity Indicators Aggregate indicator as described below.

[0035] Table 1: Introduction to Stock Trading Indicators

[0036]

[0037] Table 2 Introduction to Stock Fundamental Indicators

[0038]

[0039] The candidate stock pool is denoted as {S 1 ,S 2 ,...,S i}, where S i Represents the i-th stock in the candidate stock pool, and the maximum value of i represents the number ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a risk dispersion type stock selection algorithm based on stock association network clustering, which comprises the following steps: firstly, extracting nonlinear kernel principal component features from individual stock transaction indexes and fundamental indexes, and constructing an association network capable of representing individual stock global connection relationships in a candidate stock pool through similarity measurement between the kernel principal component features; and further, based on the individual stock association network, a Louvain algorithm is adopted to divide class clusters for the candidate stock pool, stocks to be purchased are selected from the class clusters, finally, a series of operations of stock association network construction-stock clustering-stock selection transaction are iteratively executed in the investment date range by taking weekly as a unit, and a diversified stock investment portfolio is dynamically generated. The problem that the risk level of the stock portfolio is high due to high individual stock relevancy is solved, and the income-risk ratio of the stock portfolio is increased.

Description

technical field [0001] The invention belongs to the technical field of financial quantitative investment, and relates to a risk-dispersed stock selection algorithm based on stock correlation network clustering. Background technique [0002] Stock selection is a key issue in investment management, which has a direct impact on the risk and return of investment strategies. With the continuous growth of China's stock market, the number of stocks in the A-share market is also increasing, and the difficulty of covering the entire market for investment analysis is gradually increasing. Due to the close relationship between fundamentals or technical trends, some stocks show a strong linkage law, which is very unfavorable for risk diversification in stock investment. Think about such a scenario: If in stock investment, investors allocate most of their funds to a group of highly correlated stocks, then such a stock portfolio will not only bear the volatility risk of the entire stock ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06Q40/06G06Q40/04G06K9/62
CPCG06Q40/06G06Q40/04G06F18/23G06F18/24
Inventor 冯宏伟刘娜胡陟张若鹏冯筠
Owner NORTHWEST UNIV(CN)
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com